Abstract
Artificial Neural Networks were first made as a component of extensive research attempts around man-made brainpower. They have discovered most of their usage in applications that are hard to express with conventional computer algorithms utilizing rule based programming. In competitive programming, the online judge presents a set of logical or mathematical problems to competitors. The contenders are required to develop computer programs to solve them. At present, the problems are labeled by users and are dubious. There is no reliable framework to recommend analogous problems. Our proposed system comprises of building a Convolution Neural Network (CNN) to perceive programming techniques utilized in the C++ program solutions. In our experiment, the considered domains are segment tree, binary search, dynamic programming and graph. The end goal of our system is to determine the approach required to solve the problem. Problems are tagged in view of the programming approach found in the solutions that are acknowledged by the online judge. The system prescribes to undertake challenges that belong to the same domain and can be tackled with similar approaches. Solving similar problems will improve the programmer’s proficiency in that particular domain.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bezak, P.: Building recognition system based on deep learning. In: Third International Conference on Artificial Intelligence and Pattern Recognition (AIPR), pp. 1–5, Lodz, Poland (2016). https://doi.org/10.1109/ICAIPR.2016.7585230
Simard, P.Y., Steinkraus, D., Platt, J.C.: Best practices for convolutional neural networks applied to visual document analysis. In: Proceedings of the Seventh International Conference on Document Analysis and Recognition, vol. 3, pp. 958–962 (2003)
Ciresan, D.C., Meier, U., Gambardella, L.M., Schmidhuber, J.: Convolutional neural network committees for handwritten character classification. In: IEEE International Conference on Document Analysis and Recognition, pp. 1135–1139 (2011). https://doi.org/10.1109/ICDAR.2011.229
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Proceedings of Conference on Neural Information Processing System, pp. 1097–1105 (2012)
Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Codeforces. http://codeforces.com
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sudha, S., Arun Kumar, A., Muthu Nagappan, M., Suresh, R. (2018). Classification and Recommendation of Competitive Programming Problems Using CNN. In: Venkataramani, G., Sankaranarayanan, K., Mukherjee, S., Arputharaj, K., Sankara Narayanan, S. (eds) Smart Secure Systems – IoT and Analytics Perspective. ICIIT 2017. Communications in Computer and Information Science, vol 808. Springer, Singapore. https://doi.org/10.1007/978-981-10-7635-0_20
Download citation
DOI: https://doi.org/10.1007/978-981-10-7635-0_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-7634-3
Online ISBN: 978-981-10-7635-0
eBook Packages: Computer ScienceComputer Science (R0)